Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1873 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.4525. Min Act: -0.1700

Data Index: 254313 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.4212. Min Act: -0.1700

Data Index: 966620 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.4525. Min Act: -0.1700

Data Index: 276479 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.3900. Min Act: -0.1700

Data Index: 496435 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.3900. Min Act: -0.1700

Data Index: 322339 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.3275. Min Act: -0.1700

Data Index: 1053633 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.2650. Min Act: -0.1700

Data Index: 1312522 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.2962. Min Act: -0.1700

Data Index: 26471 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.2650. Min Act: -0.1700

Data Index: 952409 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.2650. Min Act: -0.1700

Data Index: 1164701 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.2650. Min Act: -0.1700

Data Index: 501387 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.2962. Min Act: -0.1700

Data Index: 1187182 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.3587. Min Act: -0.1700

Data Index: 962200 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.3275. Min Act: -0.1700

Data Index: 282597 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.3275. Min Act: -0.1700

Data Index: 1092779 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.2962. Min Act: -0.1700

Data Index: 165095 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.2650. Min Act: -0.1700

Data Index: 825449 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.2650. Min Act: -0.1700

Data Index: 309161 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.1712. Min Act: -0.1700

Data Index: 376347 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 5.4525. Min Range: -5.4525

Max Act: 5.2962. Min Act: -0.1700

Data Index: 389890 (C4 (Web Text))

Max Activating Token Index: 997